syorami / Ddc Transfer Learning
A simple implementation of Deep Domain Confusion: Maximizing for Domain Invariance
Stars: ✭ 83
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Ddc Transfer Learning
Transformers-Domain-Adaptation
Adapt Transformer-based language models to new text domains
Stars: ✭ 67 (-19.28%)
Mutual labels: transfer-learning, domain-adaptation
KD3A
Here is the official implementation of the model KD3A in paper "KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation".
Stars: ✭ 63 (-24.1%)
Mutual labels: transfer-learning, domain-adaptation
meta-learning-progress
Repository to track the progress in Meta-Learning (MtL), including the datasets and the current state-of-the-art for the most common MtL problems.
Stars: ✭ 26 (-68.67%)
Mutual labels: transfer-learning, domain-adaptation
Libtlda
Library of transfer learners and domain-adaptive classifiers.
Stars: ✭ 71 (-14.46%)
Mutual labels: transfer-learning, domain-adaptation
Multitask Learning
Awesome Multitask Learning Resources
Stars: ✭ 361 (+334.94%)
Mutual labels: transfer-learning, domain-adaptation
Transfer-learning-materials
resource collection for transfer learning!
Stars: ✭ 213 (+156.63%)
Mutual labels: transfer-learning, domain-adaptation
cmd
Central Moment Discrepancy for Domain-Invariant Representation Learning (ICLR 2017, keras)
Stars: ✭ 53 (-36.14%)
Mutual labels: transfer-learning, domain-adaptation
Clan
( CVPR2019 Oral ) Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation
Stars: ✭ 248 (+198.8%)
Mutual labels: transfer-learning, domain-adaptation
Cross Domain ner
Cross-domain NER using cross-domain language modeling, code for ACL 2019 paper
Stars: ✭ 67 (-19.28%)
Mutual labels: transfer-learning, domain-adaptation
adapt
Awesome Domain Adaptation Python Toolbox
Stars: ✭ 46 (-44.58%)
Mutual labels: transfer-learning, domain-adaptation
pykale
Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for interdisciplinary research, part of the 🔥PyTorch ecosystem
Stars: ✭ 381 (+359.04%)
Mutual labels: transfer-learning, domain-adaptation
Transferlearning
Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习
Stars: ✭ 8,481 (+10118.07%)
Mutual labels: transfer-learning, domain-adaptation
transfertools
Python toolbox for transfer learning.
Stars: ✭ 22 (-73.49%)
Mutual labels: transfer-learning, domain-adaptation
BA3US
code for our ECCV 2020 paper "A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation"
Stars: ✭ 31 (-62.65%)
Mutual labels: transfer-learning, domain-adaptation
TA3N
[ICCV 2019 Oral] TA3N: https://github.com/cmhungsteve/TA3N (Most updated repo)
Stars: ✭ 45 (-45.78%)
Mutual labels: transfer-learning, domain-adaptation
transfer-learning-algorithms
Implementation of many transfer learning algorithms in Python with Jupyter notebooks
Stars: ✭ 42 (-49.4%)
Mutual labels: transfer-learning, domain-adaptation
Seg Uncertainty
IJCAI2020 & IJCV 2020 🌇 Unsupervised Scene Adaptation with Memory Regularization in vivo
Stars: ✭ 202 (+143.37%)
Mutual labels: transfer-learning, domain-adaptation
Awesome Domain Adaptation
A collection of AWESOME things about domian adaptation
Stars: ✭ 3,357 (+3944.58%)
Mutual labels: transfer-learning, domain-adaptation
SHOT-plus
code for our TPAMI 2021 paper "Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer"
Stars: ✭ 46 (-44.58%)
Mutual labels: transfer-learning, domain-adaptation
Transfer Learning Library
Transfer-Learning-Library
Stars: ✭ 678 (+716.87%)
Mutual labels: transfer-learning, domain-adaptation
DDC-transfer-learning
A simple implementation of Deep Domain Confusion: Maximizing for Domain Invariance which is inspired by transferlearning. The project contains Pytorch code for fine-tuning Alexnet as well as DDCnet implemented according to the original paper which adds an adaptation layer into the Alexnet. The office31 dataset used in the paper is also used in this implementation to test the performance of fine-tuning Alexnet and DDCnet with additional linear MMD loss.
Run the work
- Run command
python alextnet_finetune.pyto fine-tune a pretrained Alexnet on office31 dataset with full-training. - Run command
python DDC.pyto fine-tune a pretrained Alexnet on office31 dataset with full-training.
Experiment Results
Here we have to note that full-training protocol, which is taking all the samples from one domain as the source or target domain, and dowm-sample protocol, which is choosing 20 or 8 samples per category to use as the domain data, are quite different data preparation methods with different experiment results.
| Methods | Results (amazon to webcame) |
|---|---|
| fine-tuning Alexnet (full-training) in Pytorch | Around 51% |
| DDC ( pretrained Alexnet with adaptation layer and MMD loss) in Pytorch | Around 56% |
Future work
- [ ] Write data loader using down-sample protocol mentioned in the paper instead of using full-training protocol.
- [ ] Considering trying a tensorflow version to see if frameworks can have a difference on final experiment results.
Reference
Tzeng E, Hoffman J, Zhang N, et al. Deep domain confusion: Maximizing for domain invariance[J]. arXiv preprint arXiv:1412.3474, 2014.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].